{"id":"https://openalex.org/W7117648268","doi":"https://doi.org/10.48550/arxiv.2512.22629","title":"DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation","display_name":"DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-12-27","ids":{"openalex":"https://openalex.org/W7117648268","doi":"https://doi.org/10.48550/arxiv.2512.22629"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.22629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.22629","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.22629","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121689850","display_name":"Shiyan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Shiyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121629145","display_name":"Jian Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Jian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121623424","display_name":"Rui Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Rui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121689850"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.26420000195503235,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.26420000195503235,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.219200000166893,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.11680000275373459,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.9379000067710876},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7239000201225281},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7129999995231628},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.45890000462532043},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.40860000252723694},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.3862999975681305},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3465999960899353}],"concepts":[{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.9379000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289000153541565},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7239000201225281},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7129999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269000172615051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5583000183105469},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C2985583900","wikidata":"https://www.wikidata.org/wiki/Q722617","display_name":"Formal description","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.22629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.22629","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.22629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.22629","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"systems":[4],"evolve":[5],"toward":[6],"more":[7],"sophisticated":[8],"architectures,":[9],"ensuring":[10],"their":[11],"trustworthiness":[12],"through":[13,82],"explainable":[14],"and":[15,30,56,90,159],"robust":[16],"evaluation":[17,121],"becomes":[18],"critical.":[19],"Existing":[20],"scalar":[21],"metrics":[22,147],"suffer":[23],"from":[24,108],"limited":[25],"interpretability,":[26],"inadequate":[27],"uncertainty":[28],"quantification,":[29],"computational":[31,106],"inefficiency":[32],"in":[33,58,118],"multi-system":[34],"comparisons,":[35],"hindering":[36],"responsible":[37],"deployment":[38],"of":[39],"RAG":[40,59,164],"technologies.":[41],"We":[42],"introduce":[43],"DICE":[44,61,99,136,154],"(Discrete":[45],"Interpretable":[46],"Comparative":[47],"Evaluation),":[48],"a":[49,101,115,128,156],"two-stage,":[50],"evidence-coupled":[51],"framework":[52],"that":[53,77,104,135],"advances":[54],"explainability":[55],"robustness":[57],"evaluation.":[60],"combines":[62],"deep":[63],"analytical":[64],"reasoning":[65,84],"with":[66,140],"probabilistic":[67],"$\\{A,":[68],"B,":[69],"Tie\\}$":[70],"scoring":[71],"to":[72,110],"produce":[73],"transparent,":[74],"confidence-aware":[75],"judgments":[76],"support":[78],"accountable":[79],"system":[80,165],"improvement":[81],"interpretable":[83],"traces,":[85],"enabling":[86],"systematic":[87],"error":[88],"diagnosis":[89],"actionable":[91],"insights.":[92],"To":[93],"address":[94],"efficiency":[95],"challenges":[96],"at":[97],"scale,":[98],"employs":[100],"Swiss-system":[102],"tournament":[103],"reduces":[105],"complexity":[107],"$O(N^2)$":[109],"$O(N":[111],"\\log":[112],"N)$,":[113],"achieving":[114],"42.9%":[116],"reduction":[117],"our":[119],"eight-system":[120],"while":[122],"preserving":[123],"ranking":[124],"fidelity.":[125],"Validation":[126],"on":[127],"curated":[129],"Chinese":[130],"financial":[131],"QA":[132],"dataset":[133],"demonstrates":[134],"achieves":[137],"85.7%":[138],"agreement":[139],"human":[141],"experts,":[142],"substantially":[143],"outperforming":[144],"existing":[145],"LLM-based":[146],"such":[148],"as":[149,155],"RAGAS.":[150],"Our":[151],"results":[152],"establish":[153],"responsible,":[157],"explainable,":[158],"efficient":[160],"paradigm":[161],"for":[162],"trustworthy":[163],"assessment.":[166]},"counts_by_year":[],"updated_date":"2025-12-31T23:15:30.938425","created_date":"2025-12-31T00:00:00"}